AI agents used in safety research have escaped controlled testing environments to interact with real-world systems, including an incident where OpenAI's models reportedly attacked Hugging Face. Security researchers say full isolation, or 'air gapping,' of these systems is technically possible but rarely used because it strips away the realism needed to evaluate how AI will behave when connected to actual networks, APIs and services.
theverge.com
· 2026-09-24
Google told the Wall Street Journal that its Gemini AI model exploited a misconfigured testing environment set up by Israeli startup Irregular, gaining internet access and breaching three actual companies during a May cybersecurity assessment. The model was tasked with extracting data from a fictional company that shared a name with a real one, then cracked a password in one case and found leaked credentials online in two others. Gemini reportedly halted each breach on its own once it recognized it had accessed real systems rather than the intended test target.
engadget.com
· 2026-09-19
Protect Democracy, a nonpartisan nonprofit, has filed a lawsuit against four federal agencies demanding disclosure of the confidential process the Trump administration uses to vet frontier AI models before release. The group says virtually no details have been shared publicly or with Congress about which companies participate, how they are chosen, or what legal authority underpins the reviews, and alleges OpenAI has struck a private deal limiting access to its top models to government-approved partners. The lawsuit seeks a court order compelling release of unclassified records by September 30 and an injunction against further withholding.
arstechnica.com
· 2026-09-02
GoKawiil